Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    defining concepts and proposals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нь
    0.54
    亗
    0.51
     ку
    0.50
    чу
    0.48
    盽
    0.48
     Без
    0.48
     салу
    0.48
    栻
    0.48
     Са
    0.47
    бль
    0.47
    POSITIVE LOGITS
     CET
    0.47
     oppose
    0.44
     tours
    0.43
     jewelry
    0.41
     when
    0.41
     desserts
    0.41
    essi
    0.40
    eware
    0.40
     during
    0.40
     converted
    0.40
    Act Density 0.001%

    No Known Activations